List your company
ResearchFormerly WizWand

Multi-hop Question Answering on Bamboogle (standard val)

40Exact Match (EM)StepSearch-instruct
-1.69.22030.8Mar 14, 2026
Updated 7mo ago

Evaluation results

MethodLinks
StepSearch-instructType=Agentic RAG, Backbone=Qwen2.5-7B-Instruct2026.0340
Apex-SearcherType=Agentic RAG, Backbone=Qwen2.5-7B-Instruct2026.0340
DecEx-RAGType=Agentic RAG, Backbone=Qwen2.5-7B-Instruct2026.0337.6
Search-R1-InstructType=Agentic RAG, Backbone=Qwen2.5-7B-Instruct2026.0336.8
ReasonRAGType=Agentic RAG, Backbone=Qwen2.5-7B-Instruct2026.0336
Apex-SearcherType=Agentic RAG, Backbone=Qwen2.5-3B-Instruct2026.0335.2
StepSearch-instructType=Agentic RAG, Backbone=Qwen2.5-3B-Instruct2026.0332.8
Search-o1Type=Agentic RAG, Backbone=Qwen2.5-3B-Instruct2026.0332
Search-o1Type=Agentic RAG, Backbone=Qwen2.5-7B-Instruct2026.0329.6
ZeroSearch-instructType=Agentic RAG, Backbone=Qwen2.5-7B-Instruct2026.0327.8
IRCoTType=Iterative RAG, Backbone=Qwen2.5-3B-Instruct2026.0324
CoTType=Non-Retrieval, Backbone=Qwen2.5-7B-Instruct2026.0323.2
IRCoTType=Iterative RAG, Backbone=Qwen2.5-7B-Instruct2026.0322.4
RAGType=Standard RAG, Backbone=Qwen2.5-7B-Instruct2026.0320.8
Direct InferenceType=Non-Retrieval, Backbone=Qwen2.5-7B-Instruct2026.0312
ZeroSearch-instructType=Agentic RAG, Backbone=Qwen2.5-3B-Instruct2026.0311.1
Search-R1-InstructType=Agentic RAG, Backbone=Qwen2.5-3B-Instruct2026.038.8
RAGType=Standard RAG, Backbone=Qwen2.5-3B-Instruct2026.038
Direct InferenceType=Non-Retrieval, Backbone=Qwen2.5-3B-Instruct2026.032.4
CoTType=Non-Retrieval, Backbone=Qwen2.5-3B-Instruct2026.030